Update app.py

app.py

@@ -1,24 +1,22 @@
 import streamlit as st
-from transformers import AutoModelForCausalLM, AutoTokenizer
+from llama_cpp import Llama
 
-# Load the model and tokenizer
+# Load the GGUF model
 @st.cache_resource
 def load_model():
-    model_name = "shanthi-323/lora_model_qnachatbot_cbt_q4_k_m"
-    tokenizer = AutoTokenizer.from_pretrained(model_name)
-    model = AutoModelForCausalLM.from_pretrained(model_name)
-    return tokenizer, model
+    model_path = "shanthi-323/lora_model_qnachatbot_cbt_q4_k_m"  # Ensure this path matches your uploaded GGUF model file
+    return Llama(model_path=model_path)
 
-tokenizer, model = load_model()
+llm = load_model()
 
-st.title("AI Chatbot")
-st.write("Chat with your fine-tuned model!")
+st.title("Chat with GGUF Model")
+st.write("Start interacting with your fine-tuned chatbot!")
 
 # User input
 user_input = st.text_input("You: ", placeholder="Type your message here...")
 
 if user_input:
-    inputs = tokenizer(user_input, return_tensors="pt")
-    outputs = model.generate(inputs["input_ids"], max_length=100)
-    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
-    st.text_area("Bot:", value=response, height=200, max_chars=None)
+    # Generate a response using llama-cpp-python
+    response = llm(user_input)
+    st.text_area("Bot:", value=response["choices"][0]["text"].strip(), height=200)
+